Pith. sign in

REVIEW 4 cited by

Vision-Language Models Can Self-Improve Reasoning via Reflection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.00855 v1 pith:4KYA6NCN submitted 2024-10-30 cs.LG cs.AIcs.CLcs.CV

classification cs.LGcs.AIcs.CLcs.CV
keywords reasoningmultimodalrationalevision-languageframeworkiterativelyllmsmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Chain-of-thought (CoT) has proven to improve the reasoning capability of large language models (LLMs). However, due to the complexity of multimodal scenarios and the difficulty in collecting high-quality CoT data, CoT reasoning in multimodal LLMs has been largely overlooked. To this end, we propose a simple yet effective self-training framework, R3V, which iteratively enhances the model's Vision-language Reasoning by Reflecting on CoT Rationales. Our framework consists of two interleaved parts: (1) iteratively bootstrapping positive and negative solutions for reasoning datasets, and (2) reflection on rationale for learning from mistakes. Specifically, we introduce the self-refine and self-select losses, enabling the model to refine flawed rationale and derive the correct answer by comparing rationale candidates. Experiments on a wide range of vision-language tasks show that R3V consistently improves multimodal LLM reasoning, achieving a relative improvement of 23 to 60 percent over GPT-distilled baselines. Additionally, our approach supports self-reflection on generated solutions, further boosting performance through test-time computation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Egocentric Bias in Vision-Language Models

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Most vision-language models fail Level-2 visual perspective taking: they report the camera's view rather than the 180°-rotated string, even though they often recognize that another agent sees differently.

  2. ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures

    cs.AI 2026-04 unverdicted novelty 5.0 of 10

    ReCAPA uses multi-level predictive correction and semantic alignment modules to reduce cascading failures in VLA systems, with new metrics for tracking error propagation and recovery on embodied benchmarks.

  3. ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures

    cs.AI 2026-04 unverdicted novelty 5.0 of 10

    ReCAPA adds predictive correction and multi-level semantic alignment to VLA models, plus two new metrics for tracking error spread and recovery, yielding competitive benchmark results over LLM baselines.

  4. Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

    cs.AI 2025-03 unverdicted novelty 5.0 of 10

    The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.

Pith tools